sophosympatheia/Evathene-v1.2

Full fine-tune vs EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2. Fine-tune: 96% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 0/1, Norms 145/161, MLP 235/240, Attention 550/560, lm_head 1/1

2 derivatives checked

• mradermacher/Evathene-v1.2-i1-GGUF: Quantization
• mradermacher/Evathene-v1.2-GGUF: Quantization

On the Hub · Downloads on Model Pulse